x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 195 insertions, 0 deletions

diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c
new file mode 100644
index 000000000..f751d743a
--- /dev/null
+++ b/drivers/tee/optee/device.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/tee_core.h>
+#include <linux/uuid.h>
+#include "optee_private.h"
+
+static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)
+{
+	return (ver->impl_id == TEE_IMPL_ID_OPTEE);
+}
+
+static int get_devices(struct tee_context *ctx, u32 session,
+		       struct tee_shm *device_shm, u32 *shm_size,
+		       u32 func)
+{
+	int ret = 0;
+	struct tee_ioctl_invoke_arg inv_arg;
+	struct tee_param param[4];
+
+	memset(&inv_arg, 0, sizeof(inv_arg));
+	memset(&param, 0, sizeof(param));
+
+	inv_arg.func = func;
+	inv_arg.session = session;
+	inv_arg.num_params = 4;
+
+	/* Fill invoke cmd params */
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+	param[0].u.memref.shm = device_shm;
+	param[0].u.memref.size = *shm_size;
+	param[0].u.memref.shm_offs = 0;
+
+	ret = tee_client_invoke_func(ctx, &inv_arg, param);
+	if ((ret < 0) || ((inv_arg.ret != TEEC_SUCCESS) &&
+			  (inv_arg.ret != TEEC_ERROR_SHORT_BUFFER))) {
+		/*
+		 * TEE_ERROR_STORAGE_NOT_AVAILABLE is returned when getting
+		 * the list of device TAs that depends on RPMB but a usable
+		 * RPMB device isn't found.
+		 */
+		if (inv_arg.ret == TEE_ERROR_STORAGE_NOT_AVAILABLE)
+			return -ENODEV;
+		pr_err("PTA_CMD_GET_DEVICES invoke function err: %x\n",
+		       inv_arg.ret);
+		return -EINVAL;
+	}
+
+	*shm_size = param[0].u.memref.size;
+
+	return 0;
+}
+
+static void optee_release_device(struct device *dev)
+{
+	struct tee_client_device *optee_device = to_tee_client_device(dev);
+
+	kfree(optee_device);
+}
+
+static ssize_t need_supplicant_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	return 0;
+}
+
+static DEVICE_ATTR_RO(need_supplicant);
+
+static int optee_register_device(const uuid_t *device_uuid, u32 func)
+{
+	struct tee_client_device *optee_device = NULL;
+	int rc;
+
+	optee_device = kzalloc_obj(*optee_device);
+	if (!optee_device)
+		return -ENOMEM;
+
+	optee_device->dev.bus = &tee_bus_type;
+	optee_device->dev.release = optee_release_device;
+	if (dev_set_name(&optee_device->dev, "optee-ta-%pUb", device_uuid)) {
+		kfree(optee_device);
+		return -ENOMEM;
+	}
+	uuid_copy(&optee_device->id.uuid, device_uuid);
+
+	rc = device_register(&optee_device->dev);
+	if (rc) {
+		pr_err("device registration failed, err: %d\n", rc);
+		put_device(&optee_device->dev);
+		return rc;
+	}
+
+	if (func == PTA_CMD_GET_DEVICES_SUPP)
+		device_create_file(&optee_device->dev,
+				   &dev_attr_need_supplicant);
+
+	return 0;
+}
+
+static int __optee_enumerate_devices(u32 func)
+{
+	const uuid_t pta_uuid =
+		UUID_INIT(0x7011a688, 0xddde, 0x4053,
+			  0xa5, 0xa9, 0x7b, 0x3c, 0x4d, 0xdf, 0x13, 0xb8);
+	struct tee_ioctl_open_session_arg sess_arg;
+	struct tee_shm *device_shm = NULL;
+	const uuid_t *device_uuid = NULL;
+	struct tee_context *ctx = NULL;
+	u32 shm_size = 0, idx, num_devices = 0;
+	int rc;
+
+	memset(&sess_arg, 0, sizeof(sess_arg));
+
+	/* Open context with OP-TEE driver */
+	ctx = tee_client_open_context(NULL, optee_ctx_match, NULL, NULL);
+	if (IS_ERR(ctx))
+		return -ENODEV;
+
+	/* Open session with device enumeration pseudo TA */
+	export_uuid(sess_arg.uuid, &pta_uuid);
+	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
+	sess_arg.num_params = 0;
+
+	rc = tee_client_open_session(ctx, &sess_arg, NULL);
+	if ((rc < 0) || (sess_arg.ret != TEEC_SUCCESS)) {
+		/* Device enumeration pseudo TA not found */
+		rc = 0;
+		goto out_ctx;
+	}
+
+	rc = get_devices(ctx, sess_arg.session, NULL, &shm_size, func);
+	if (rc < 0 || !shm_size)
+		goto out_sess;
+
+	device_shm = tee_shm_alloc_kernel_buf(ctx, shm_size);
+	if (IS_ERR(device_shm)) {
+		pr_err("tee_shm_alloc_kernel_buf failed\n");
+		rc = PTR_ERR(device_shm);
+		goto out_sess;
+	}
+
+	rc = get_devices(ctx, sess_arg.session, device_shm, &shm_size, func);
+	if (rc < 0)
+		goto out_shm;
+
+	device_uuid = tee_shm_get_va(device_shm, 0);
+	if (IS_ERR(device_uuid)) {
+		pr_err("tee_shm_get_va failed\n");
+		rc = PTR_ERR(device_uuid);
+		goto out_shm;
+	}
+
+	num_devices = shm_size / sizeof(uuid_t);
+
+	for (idx = 0; idx < num_devices; idx++) {
+		rc = optee_register_device(&device_uuid[idx], func);
+		if (rc)
+			goto out_shm;
+	}
+
+out_shm:
+	tee_shm_free(device_shm);
+out_sess:
+	tee_client_close_session(ctx, sess_arg.session);
+out_ctx:
+	tee_client_close_context(ctx);
+
+	return rc;
+}
+
+int optee_enumerate_devices(u32 func)
+{
+	return  __optee_enumerate_devices(func);
+}
+
+static int __optee_unregister_device(struct device *dev, void *data)
+{
+	if (!strncmp(dev_name(dev), "optee-ta", strlen("optee-ta")))
+		device_unregister(dev);
+
+	return 0;
+}
+
+void optee_unregister_devices(void)
+{
+	bus_for_each_dev(&tee_bus_type, NULL, NULL,
+			 __optee_unregister_device);
+}